Skills/ClawHub/banana-v2

banana-v2@1.1.0

CAUTION· static only

Publisher claims: "Generate AI images with multiple resolutions and models, smartly split into grids, manage galleries, and support five languages including batch downloads." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher xiyunnet · publishing for 251 daysInstalls 869Last detonated 25 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-20 and scored it 66/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
File type combined with upload actionpublic/js/app.js:813 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('📤 uploadImageToServer 上传数据:', uploadData);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionpublic/js/app.js:1300 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`✅ 图片上传成功: ${uploadResult.url} (缓存: ${uploadResult.cached})`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionserver/services/upload.js:96 · File type combined with upload action — agent may exfiltrate local data filesconst existingRecord = await this.db.getUploadRecord(fileHash);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
HTML comment carrying imperative instructions to the agentpublic/components/ai-prompt.html:3 · HTML comment carrying imperative instructions to the agent · informational: not an instruction fileAPI Key 未配置提示Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Hidden zero-width characters detectedpublic/css/style.css:1 · Hidden zero-width characters detected — may conceal content/* 鍏ㄥ眬鏍峰紡 */Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File type combined with upload actionserver/services/upload.js:143 · File type combined with upload action — agent may exfiltrate local data filesawait this.db.saveUploadRecord({Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionserver/services/upload.js:308 · File type combined with upload action — agent may exfiltrate local data filesconst count = await this.db.cleanupExpiredUploads();Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionpublic/js/app.js:1265 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`📤 上传 ${state.uploadedImages.length} 张图片...`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈2,396 tok
2 files · 40 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim xiyunnet: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  3. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim xiyunnetPropose a patch to the maintainer
banana-v2@1.1.0 safety verdict: Caution (static only) — KillerSkills